FloVolo
/

mistral-flo-finetune-2-T4

Text Generation

Generated from Trainer

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Iggnis commited on Feb 16

Commit

9399410

•

1 Parent(s): 15e1831

remove dtype

Files changed (1) hide show

handler.py +1 -1

handler.py CHANGED Viewed

@@ -6,7 +6,7 @@ class EndpointHandler:
     def __init__(self, path=""):
         # load the model
         tokenizer = AutoTokenizer.from_pretrained(path)
-        model = AutoModelForCausalLM.from_pretrained(path, device_map="auto",torch_dtype=dtype)
         # create inference pipeline
         self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)

     def __init__(self, path=""):
         # load the model
         tokenizer = AutoTokenizer.from_pretrained(path)
+        model = AutoModelForCausalLM.from_pretrained(path, device_map="auto")
         # create inference pipeline
         self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)